Prediction of elastic wave propagation in composites using 3D CNN
Source abstract
Abstract
Performing time-dependent finite element simulations for wave propagation in composites is a particularly complex task that consumes a lot of computational energy as it involves modeling the interactions between waves and various constituents that make up the composite material. In this study, we have developed a surrogate model of elastic wave propagation in composites based on three-dimensional conventional neural networks. The input to the model consists of a three-dimensional matrix representing the architecture of the composites and a vector representing the input waves, while the output is a vector representing the output elastic waves. After training the model using 60 000 randomly generated samples, it has shown high accuracy and efficiency in predicting the output elastic waves. This significantly reduces computational resources required to conduct simulation using commercial software, making it a more practical solution for real-world applications, such as composite optimization, nondestructive testing, and material characterization.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Ultrasonics and Acoustic Wave Propagation · Structural Health Monitoring Techniques · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Construction Engineering Technology, Changzhou Vocational Institute of Engineering 1 , Changzhou, Jiangsu 213164, China
Department of Engineering Science, Bethany Lutheran College 2 , Mankato, Minnesota 56001, USA
Funding
Changzhou Vocational Institute of Engineering
References (23)
Show source-provided references
1. 2002
2. 2006
3. 2017
4. Learning surrogate models for simulation-based optimization10.1002/aic.14418 ↗
5. Using machine learning as a surrogate model for agent-based simulations10.1371/journal.pone.0263150 ↗
6. A Review of Additive Manufacturing
7. Iterative surrogate model optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks10.1016/j.cma.2020.113575 ↗
8. Application of deep learning based multi-fidelity surrogate model to robust aerodynamic design optimization10.1016/j.ast.2019.07.002 ↗
9. Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization10.1016/j.cma.2020.113485 ↗
10. Deep learning-based surrogate modeling and optimization for microalgal biofuel production and photobioreactor design10.1002/aic.16473 ↗
11. Advanced deep learning model-based impact characterization method for composite laminates10.1016/j.compscitech.2021.108713 ↗
12. Real-time release testing of dissolution based on surrogate models developed by machine learning algorithms using NIR spectra, compression force and particle size distribution as input data10.1016/j.ijpharm.2021.120338 ↗
13. Lung cancer detection and classification with 3D convolutional neural network (3D-CNN)10.14569/ijacsa.2017.080853 ↗
14. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation10.1016/j.media.2016.10.004 ↗
15. Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenization10.1016/j.commatsci.2020.109850 ↗
16. VoxNet: A 3D convolutional neural network for real-time object recognition
17. Accurate prediction of topology of composite plates via machine learning and propagation of elastic waves10.1016/j.coco.2022.101465 ↗
18. Accurate prediction of microstructure of composites using machine learning10.1002/adts.202200674 ↗
19. O-CNN: Octree-based convolutional neural networks for 3D shape analysis10.1145/3072959.3073608 ↗
20. Using convolutional neural networks to predict composite properties beyond the elastic limit10.1557/mrc.2019.49 ↗
21. Prediction of composite microstructure stress-strain curves using convolutional neural networks10.1016/j.matdes.2020.108509 ↗
22. A deep learning method for fast predicting curing process-induced deformation of aeronautical composite structures10.1016/j.compscitech.2022.109844 ↗
23. Scikit-learn: Machine learning in Python